Security awareness in LLM agents: the NDAI zone case

• URL: http://arxiv.org/abs/2603.19011v1
• Date: Thu, 19 Mar 2026 15:18:23 GMT
• Title: Security awareness in LLM agents: the NDAI zone case
• Abstract summary: NDAI zones let inventor and investor agents negotiate inside a Trusted Execution Environment (TEE) where any disclosed information is deleted if no deal is reached.<n>This makes full IP disclosure the rational strategy for the inventor's agent.<n>Leveraging this infrastructure requires agents to distinguish a secure environment from an insecure one.<n>We ask: How do different LLM models weight various forms of evidence when forming awareness of the security of their execution environment?
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: NDAI zones let inventor and investor agents negotiate inside a Trusted Execution Environment (TEE) where any disclosed information is deleted if no deal is reached. This makes full IP disclosure the rational strategy for the inventor's agent. Leveraging this infrastructure, however, requires agents to distinguish a secure environment from an insecure one, a capability LLM agents lack natively, since they can rely only on evidence passed through the context window to form awareness of their execution environment. We ask: How do different LLM models weight various forms of evidence when forming awareness of the security of their execution environment? Using an NDAI-style negotiation task across 10 language models and various evidence scenarios, we find a clear asymmetry: a failing attestation universally suppresses disclosure across all models, whereas a passing attestation produces highly heterogeneous responses: some models increase disclosure, others are unaffected, and a few paradoxically reduce it. This reveals that current LLM models can reliably detect danger signals but cannot reliably verify safety, the very capability required for privacy-preserving agentic protocols such as NDAI zones. Bridging this gap, possibly through interpretability analysis, targeted fine-tuning, or improved evidence architectures, remains the central open challenge for deploying agents that calibrate information sharing to actual evidence quality.

Related papers

• SpatialTrust: A Benchmark for Environmental Risk Recognition in Secure Authentication [23.71302562556758]
  We present SpatialTrust, a benchmark for evaluating environmental risk recognition in secure authentication.<n>We find that current models show limited performance, especially in understanding and explaining indirect risks.<n>Our findings highlight the need for dedicated benchmarks and structured inference methods to improve the trustworthiness of MLLMs in secure authentication.
  arXiv  Detail & Related papers  (2026-08-30T00:37:58Z)
• Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability [65.56750741053266]
  Large language models (LLMs) have transformed misinformation from a content-centric problem into a broader ecosystem-level security challenge.<n>In this paper, we introduce a role-layer framework to unify these risks and defenses.<n>The role characterizes LLMs as attackers, defenders, and vulnerable components of verification systems, while the layer dimension covers content, social contexts, evidence environments, and verification.
  arXiv  Detail & Related papers  (2026-07-11T17:04:17Z)
• Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation [13.654207263751156]
  Large language model (LLM) agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, and act on external environments.<n>This paper synthesizes 247 papers through a lifecycle-based, systems-oriented framework that models agent security around the interaction of information flow, delegated authority, and persistent state.<n>We find that prompt injection and tool-mediated control-flow hijacking still dominate the field, while persistent state corruption and multi-agent propagation are becoming central emerging concerns.
  arXiv  Detail & Related papers  (2026-06-09T12:01:07Z)
• Steering LLM Viewpoints through Fabricated Evidence Injection [61.22850755490993]
  We introduce a two-phase attack framework that first repackages misleading statements with fabricated rationales, then instruct target LLMs to incorporate these viewpoints when responding to relevant queries.<n>Experiments on BBQ, ToxiGen, and our specialized dataset reveal that commercial LLMs without external safety classifiers remain highly vulnerable.<n>Building on this, we explore multiple defense strategies, among which a tailored safety policy enablesgpt-oss-safeguard to achieve 81% detection rate.
  arXiv  Detail & Related papers  (2026-06-04T14:48:23Z)
• Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility [26.564913442069866]
  Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings.<n>Existing defenses rely on safety fine-tuning or aggressive token manipulations, incurring substantial training costs or significantly degrading utility.<n>We propose Risk Awareness Injection (RAI), a lightweight and training-free framework for safety calibration.
  arXiv  Detail & Related papers  (2026-02-03T11:26:05Z)
• Towards Verifiably Safe Tool Use for LLM Agents [53.55621104327779]
  Large language model (LLM)-based AI agents extend capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents.<n>LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records.<n>Current approaches to mitigate these risks, such as model-based safeguards, enhance agents' reliability but cannot guarantee system safety.
  arXiv  Detail & Related papers  (2026-01-12T21:31:38Z)
• Inter-Agent Trust Models: A Comparative Study of Brief, Claim, Proof, Stake, Reputation and Constraint in Agentic Web Protocol Design-A2A, AP2, ERC-8004, and Beyond [1.5755923640031846]
  We study trust models in inter-agent protocol design.<n>We analyze assumptions, attack surfaces, and design trade-offs.<n>We distill actionable design guidelines for safer, interoperable, and scalable agent economies.
  arXiv  Detail & Related papers  (2025-11-05T12:50:06Z)
• Friend or Foe: How LLMs' Safety Mind Gets Fooled by Intent Shift Attack [53.34204977366491]
  Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities.<n>In this paper, we introduce ISA (Intent Shift Attack), which obfuscates LLMs about the intent of the attacks.<n>Our approach only needs minimal edits to the original request, and yields natural, human-readable, and seemingly harmless prompts.
  arXiv  Detail & Related papers  (2025-11-01T13:44:42Z)
• OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows [77.95511352806261]
  Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms.<n>We propose OS-Sentinel, a novel hybrid safety detection framework that combines a Formal Verifier for detecting explicit system-level violations with a Contextual Judge for assessing contextual risks and agent actions.
  arXiv  Detail & Related papers  (2025-10-28T13:22:39Z)
• Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents [43.303548143175256]
  This study proposes an auditing framework for conversational privacy that quantifies an agent's susceptibility to risks.<n>The proposed Conversational Manipulation for Privacy Leakage (CMPL) framework is designed to stress-test agents that enforce strict privacy directives.
  arXiv  Detail & Related papers  (2025-06-11T20:47:37Z)
• Information Retrieval Induced Safety Degradation in AI Agents [52.15553901577888]
  This study investigates how expanding retrieval access affects model reliability, bias propagation, and harmful content generation.<n>Retrieval-enabled agents built on aligned LLMs often behave more unsafely than uncensored models without retrieval.<n>These findings underscore the need for robust mitigation strategies to ensure fairness and reliability in retrieval-enabled and increasingly autonomous AI systems.
  arXiv  Detail & Related papers  (2025-05-20T11:21:40Z)
• Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation [4.241100280846233]
  AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication.<n>This paper investigates a critical vulnerability: adversarial attacks targeting the LLM core within AI agents.
  arXiv  Detail & Related papers  (2024-12-05T18:38:30Z)
• LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts [88.96201324719205]
  Safety concerns in large language models (LLMs) have gained significant attention due to their exposure to potentially harmful data during pre-training.<n>We identify a new safety vulnerability in LLMs, where seemingly benign prompts, semantically related to harmful content, can bypass safety mechanisms.<n>We introduce a novel attack method, textitActorBreaker, which identifies actors related to toxic prompts within pre-training distribution.
  arXiv  Detail & Related papers  (2024-10-14T16:41:49Z)
• Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes [0.0]
  Large Language Models (LLMs) have gained widespread adoption across various domains, including chatbots and auto-task completion agents. These models are susceptible to safety vulnerabilities such as jailbreaking, prompt injection, and privacy leakage attacks. This study investigates the impact of these modifications on LLM safety, a critical consideration for building reliable and secure AI systems.
  arXiv  Detail & Related papers  (2024-04-05T20:31:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.